{"id":"W2022902860","doi":"10.1145/1007568.1007621","title":"Incremental and effective data summarization for dynamic hierarchical clustering","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Automatic summarization; Computer science; Cluster analysis; Data mining; Merge (version control); Hierarchical clustering; Data stream clustering; CURE data clustering algorithm; Fuzzy clustering; Information retrieval; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001882289,0.00005814074,0.00005466382,0.00004600833,0.00008054712,0.0001846034,0.0005572718,0.00001432973,0.000001511285],"category_scores_gemma":[0.00001816066,0.00005121759,0.00000781905,0.00008813968,0.00001957758,0.001084147,0.001403899,0.00003060304,0.000003784308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002280921,"about_ca_system_score_gemma":0.000007530557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002598073,"about_ca_topic_score_gemma":0.00006403225,"domain_scores_codex":[0.9994195,0.00001027087,0.00007224458,0.0003012547,0.00008211384,0.000114638],"domain_scores_gemma":[0.9995477,0.00003577928,0.00001732303,0.0003601761,0.000008539085,0.0000304717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001456469,0.00007700621,0.0002851013,0.00006012314,0.00003983346,0.000005249403,0.0001507143,0.0001598581,0.0008013375,0.1265038,0.0003628736,0.8715395],"study_design_scores_gemma":[0.0009773996,0.00009748329,0.0041548,0.00001312327,0.000006945197,0.00000312563,0.00001422129,0.9852901,0.0001789123,0.007917391,0.001225325,0.0001212144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003406203,0.000009992616,0.9949248,0.000631233,0.0001136983,0.0003555426,0.0000210076,0.00007612826,0.0004613986],"genre_scores_gemma":[0.542189,0.00001355062,0.4569913,0.0002835257,0.00003749691,0.00002431132,0.0003299317,0.000006164526,0.0001247073],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9851302,"threshold_uncertainty_score":0.2088593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01748484195449467,"score_gpt":0.2759949414161231,"score_spread":0.2585100994616284,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}